ComfyUI Node: SDNext Merge

Authored by TechnoByteJS

Created

Updated

14 stars

Category

TechNodes/merging

Inputs

model_a
  • none
model_b
  • none
model_c
  • none
merge_mode
  • weighted_sum
  • weighted_subtraction
  • tensor_sum
  • add_difference
  • train_difference
  • sum_twice
  • triple_sum
  • euclidean_add_difference
  • multiply_difference
  • top_k_tensor_sum
  • similarity_add_difference
  • distribution_crossover
  • ties_add_difference
precision
  • fp16
  • original
weights_clip BOOLEAN
mem_device
  • cuda
  • cpu
work_device
  • cuda
  • cpu
threads INT
mbw_preset_alpha
  • none
  • GRAD_V
  • GRAD_A
  • FLAT_25
  • FLAT_75
  • WRAP08
  • WRAP12
  • WRAP14
  • WRAP16
  • MID12_50
  • OUT07
  • OUT12
  • OUT12_5
  • RING08_SOFT
  • RING08_5
  • RING10_5
  • RING10_3
  • SMOOTHSTEP
  • REVERSE_SMOOTHSTEP
  • 2SMOOTHSTEP
  • 2R_SMOOTHSTEP
  • 3SMOOTHSTEP
  • 3R_SMOOTHSTEP
  • 4SMOOTHSTEP
  • 4R_SMOOTHSTEP
  • HALF_SMOOTHSTEP
  • HALF_R_SMOOTHSTEP
  • ONE_THIRD_SMOOTHSTEP
  • ONE_THIRD_R_SMOOTHSTEP
  • ONE_FOURTH_SMOOTHSTEP
  • ONE_FOURTH_R_SMOOTHSTEP
  • COSINE
  • REVERSE_COSINE
  • CUBIC_HERMITE
  • REVERSE_CUBIC_HERMITE
  • FAKE_REVERSE_CUBIC_HERMITE
  • LOW_OFFSET_CUBIC_HERMITE
  • ALL_A
  • ALL_B
alpha FLOAT
beta FLOAT
re_basin BOOLEAN
re_basin_iterations INT
optional_model_a MODEL
optional_clip_a CLIP
optional_model_b MODEL
optional_clip_b CLIP
optional_model_c MODEL
optional_clip_c CLIP
optional_mbw_layers_alpha MBW_LAYERS

Outputs

MODEL

CLIP

Extension: TechNodes

ComfyUI nodes for merging, testing and more. NOTE: SDNext Merge, VAE Merge, MBW Layers, Repeat VAE, Quantization.

Authored by TechnoByteJS

Run ComfyUI workflows in the Cloud!

No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues

Learn more